Structurally Sparsified Backward Propagation for Faster Long Short-Term Memory Training Article Swipe
Maohua Zhu
,
Jason Clemons
,
Jeff Pool
,
Minsoo Rhu
,
Stephen W. Keckler
,
Yuan Xie
·
YOU?
·
· 2018
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.1806.00512
YOU?
·
· 2018
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.1806.00512
Exploiting sparsity enables hardware systems to run neural networks faster and more energy-efficiently. However, most prior sparsity-centric optimization techniques only accelerate the forward pass of neural networks and usually require an even longer training process with iterative pruning and retraining. We observe that artificially inducing sparsity in the gradients of the gates in an LSTM cell has little impact on the training quality. Further, we can enforce structured sparsity in the gate gradients to make the LSTM backward pass up to 45% faster than the state-of-the-art dense approach and 168% faster than the state-of-the-art sparsifying method on modern GPUs. Though the structured sparsifying method can impact the accuracy of a model, this performance gap can be eliminated by mixing our sparse training method and the standard dense training method. Experimental results show that the mixed method can achieve comparable results in a shorter time span than using purely dense training.
Related Topics
Concepts
Computer science
Pruning
Process (computing)
Speedup
Artificial neural network
Training (meteorology)
State (computer science)
Energy (signal processing)
Algorithm
Artificial intelligence
Computer engineering
Parallel computing
Mathematics
Biology
Meteorology
Operating system
Statistics
Physics
Agronomy
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/1806.00512
- https://arxiv.org/pdf/1806.00512
- OA Status
- green
- Cited By
- 7
- References
- 15
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W2806254827
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W2806254827Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.1806.00512Digital Object Identifier
- Title
-
Structurally Sparsified Backward Propagation for Faster Long Short-Term Memory TrainingWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2018Year of publication
- Publication date
-
2018-06-01Full publication date if available
- Authors
-
Maohua Zhu, Jason Clemons, Jeff Pool, Minsoo Rhu, Stephen W. Keckler, Yuan XieList of authors in order
- Landing page
-
https://arxiv.org/abs/1806.00512Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/1806.00512Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/1806.00512Direct OA link when available
- Concepts
-
Computer science, Pruning, Process (computing), Speedup, Artificial neural network, Training (meteorology), State (computer science), Energy (signal processing), Algorithm, Artificial intelligence, Computer engineering, Parallel computing, Mathematics, Biology, Meteorology, Operating system, Statistics, Physics, AgronomyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
7Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 2, 2022: 1, 2020: 2, 2019: 1, 2018: 1Per-year citation counts (last 5 years)
- References (count)
-
15Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W2806254827 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.1806.00512 |
| ids.doi | https://doi.org/10.48550/arxiv.1806.00512 |
| ids.mag | 2806254827 |
| ids.openalex | https://openalex.org/W2806254827 |
| fwci | |
| type | preprint |
| title | Structurally Sparsified Backward Propagation for Faster Long Short-Term Memory Training |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10036 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9998000264167786 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Advanced Neural Network Applications |
| topics[1].id | https://openalex.org/T12676 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9994999766349792 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Machine Learning and ELM |
| topics[2].id | https://openalex.org/T10500 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9965000152587891 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2206 |
| topics[2].subfield.display_name | Computational Mechanics |
| topics[2].display_name | Sparse and Compressive Sensing Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7830120325088501 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C108010975 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7284571528434753 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q500094 |
| concepts[1].display_name | Pruning |
| concepts[2].id | https://openalex.org/C98045186 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5943227410316467 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q205663 |
| concepts[2].display_name | Process (computing) |
| concepts[3].id | https://openalex.org/C68339613 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5509145855903625 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1549489 |
| concepts[3].display_name | Speedup |
| concepts[4].id | https://openalex.org/C50644808 |
| concepts[4].level | 2 |
| concepts[4].score | 0.54869544506073 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[4].display_name | Artificial neural network |
| concepts[5].id | https://openalex.org/C2777211547 |
| concepts[5].level | 2 |
| concepts[5].score | 0.44716912508010864 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q17141490 |
| concepts[5].display_name | Training (meteorology) |
| concepts[6].id | https://openalex.org/C48103436 |
| concepts[6].level | 2 |
| concepts[6].score | 0.42498332262039185 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q599031 |
| concepts[6].display_name | State (computer science) |
| concepts[7].id | https://openalex.org/C186370098 |
| concepts[7].level | 2 |
| concepts[7].score | 0.42013856768608093 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q442787 |
| concepts[7].display_name | Energy (signal processing) |
| concepts[8].id | https://openalex.org/C11413529 |
| concepts[8].level | 1 |
| concepts[8].score | 0.41803112626075745 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[8].display_name | Algorithm |
| concepts[9].id | https://openalex.org/C154945302 |
| concepts[9].level | 1 |
| concepts[9].score | 0.40586769580841064 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[9].display_name | Artificial intelligence |
| concepts[10].id | https://openalex.org/C113775141 |
| concepts[10].level | 1 |
| concepts[10].score | 0.335326611995697 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q428691 |
| concepts[10].display_name | Computer engineering |
| concepts[11].id | https://openalex.org/C173608175 |
| concepts[11].level | 1 |
| concepts[11].score | 0.2455286979675293 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q232661 |
| concepts[11].display_name | Parallel computing |
| concepts[12].id | https://openalex.org/C33923547 |
| concepts[12].level | 0 |
| concepts[12].score | 0.09057414531707764 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[12].display_name | Mathematics |
| concepts[13].id | https://openalex.org/C86803240 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[13].display_name | Biology |
| concepts[14].id | https://openalex.org/C153294291 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q25261 |
| concepts[14].display_name | Meteorology |
| concepts[15].id | https://openalex.org/C111919701 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[15].display_name | Operating system |
| concepts[16].id | https://openalex.org/C105795698 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[16].display_name | Statistics |
| concepts[17].id | https://openalex.org/C121332964 |
| concepts[17].level | 0 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[17].display_name | Physics |
| concepts[18].id | https://openalex.org/C6557445 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q173113 |
| concepts[18].display_name | Agronomy |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7830120325088501 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/pruning |
| keywords[1].score | 0.7284571528434753 |
| keywords[1].display_name | Pruning |
| keywords[2].id | https://openalex.org/keywords/process |
| keywords[2].score | 0.5943227410316467 |
| keywords[2].display_name | Process (computing) |
| keywords[3].id | https://openalex.org/keywords/speedup |
| keywords[3].score | 0.5509145855903625 |
| keywords[3].display_name | Speedup |
| keywords[4].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[4].score | 0.54869544506073 |
| keywords[4].display_name | Artificial neural network |
| keywords[5].id | https://openalex.org/keywords/training |
| keywords[5].score | 0.44716912508010864 |
| keywords[5].display_name | Training (meteorology) |
| keywords[6].id | https://openalex.org/keywords/state |
| keywords[6].score | 0.42498332262039185 |
| keywords[6].display_name | State (computer science) |
| keywords[7].id | https://openalex.org/keywords/energy |
| keywords[7].score | 0.42013856768608093 |
| keywords[7].display_name | Energy (signal processing) |
| keywords[8].id | https://openalex.org/keywords/algorithm |
| keywords[8].score | 0.41803112626075745 |
| keywords[8].display_name | Algorithm |
| keywords[9].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[9].score | 0.40586769580841064 |
| keywords[9].display_name | Artificial intelligence |
| keywords[10].id | https://openalex.org/keywords/computer-engineering |
| keywords[10].score | 0.335326611995697 |
| keywords[10].display_name | Computer engineering |
| keywords[11].id | https://openalex.org/keywords/parallel-computing |
| keywords[11].score | 0.2455286979675293 |
| keywords[11].display_name | Parallel computing |
| keywords[12].id | https://openalex.org/keywords/mathematics |
| keywords[12].score | 0.09057414531707764 |
| keywords[12].display_name | Mathematics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:1806.00512 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/1806.00512 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/1806.00512 |
| locations[1].id | doi:10.48550/arxiv.1806.00512 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.1806.00512 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5101831882 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-8914-9834 |
| authorships[0].author.display_name | Maohua Zhu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Maohua Zhu |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5056153489 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5533-417X |
| authorships[1].author.display_name | Jason Clemons |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Jason Clemons |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5063722719 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Jeff Pool |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Jeff Pool |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5091648103 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-3303-8681 |
| authorships[3].author.display_name | Minsoo Rhu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Minsoo Rhu |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5063354509 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-6701-6099 |
| authorships[4].author.display_name | Stephen W. Keckler |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Stephen W. Keckler |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5110042813 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-6945-7437 |
| authorships[5].author.display_name | Yuan Xie |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Yuan Xie |
| authorships[5].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/1806.00512 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2018-06-13T00:00:00 |
| display_name | Structurally Sparsified Backward Propagation for Faster Long Short-Term Memory Training |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10036 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9998000264167786 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Advanced Neural Network Applications |
| related_works | https://openalex.org/W2058965144, https://openalex.org/W2164382479, https://openalex.org/W2146343568, https://openalex.org/W98480971, https://openalex.org/W2150291671, https://openalex.org/W2013643406, https://openalex.org/W2027972911, https://openalex.org/W2157978810, https://openalex.org/W2597809628, https://openalex.org/W3046370962 |
| cited_by_count | 7 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 2 |
| counts_by_year[1].year | 2022 |
| counts_by_year[1].cited_by_count | 1 |
| counts_by_year[2].year | 2020 |
| counts_by_year[2].cited_by_count | 2 |
| counts_by_year[3].year | 2019 |
| counts_by_year[3].cited_by_count | 1 |
| counts_by_year[4].year | 2018 |
| counts_by_year[4].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:1806.00512 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/1806.00512 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/1806.00512 |
| primary_location.id | pmh:oai:arXiv.org:1806.00512 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/1806.00512 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/1806.00512 |
| publication_date | 2018-06-01 |
| publication_year | 2018 |
| referenced_works | https://openalex.org/W2285660444, https://openalex.org/W1632114991, https://openalex.org/W2183341477, https://openalex.org/W2963803379, https://openalex.org/W2594990650, https://openalex.org/W2949335953, https://openalex.org/W2516141709, https://openalex.org/W2097117768, https://openalex.org/W2589646680, https://openalex.org/W1591801644, https://openalex.org/W1861492603, https://openalex.org/W2952899695, https://openalex.org/W2407022425, https://openalex.org/W2617766261, https://openalex.org/W2513419314 |
| referenced_works_count | 15 |
| abstract_inverted_index.a | 109, 141 |
| abstract_inverted_index.We | 40 |
| abstract_inverted_index.an | 30, 53 |
| abstract_inverted_index.be | 115 |
| abstract_inverted_index.by | 117 |
| abstract_inverted_index.in | 46, 52, 69, 140 |
| abstract_inverted_index.of | 24, 49, 108 |
| abstract_inverted_index.on | 59, 96 |
| abstract_inverted_index.to | 5, 73, 80 |
| abstract_inverted_index.up | 79 |
| abstract_inverted_index.we | 64 |
| abstract_inverted_index.45% | 81 |
| abstract_inverted_index.and | 10, 27, 38, 88, 123 |
| abstract_inverted_index.can | 65, 104, 114, 136 |
| abstract_inverted_index.gap | 113 |
| abstract_inverted_index.has | 56 |
| abstract_inverted_index.our | 119 |
| abstract_inverted_index.run | 6 |
| abstract_inverted_index.the | 21, 47, 50, 60, 70, 75, 84, 92, 100, 106, 124, 133 |
| abstract_inverted_index.168% | 89 |
| abstract_inverted_index.LSTM | 54, 76 |
| abstract_inverted_index.cell | 55 |
| abstract_inverted_index.even | 31 |
| abstract_inverted_index.gate | 71 |
| abstract_inverted_index.make | 74 |
| abstract_inverted_index.more | 11 |
| abstract_inverted_index.most | 14 |
| abstract_inverted_index.only | 19 |
| abstract_inverted_index.pass | 23, 78 |
| abstract_inverted_index.show | 131 |
| abstract_inverted_index.span | 144 |
| abstract_inverted_index.than | 83, 91, 145 |
| abstract_inverted_index.that | 42, 132 |
| abstract_inverted_index.this | 111 |
| abstract_inverted_index.time | 143 |
| abstract_inverted_index.with | 35 |
| abstract_inverted_index.GPUs. | 98 |
| abstract_inverted_index.dense | 86, 126, 148 |
| abstract_inverted_index.gates | 51 |
| abstract_inverted_index.mixed | 134 |
| abstract_inverted_index.prior | 15 |
| abstract_inverted_index.using | 146 |
| abstract_inverted_index.Though | 99 |
| abstract_inverted_index.faster | 9, 82, 90 |
| abstract_inverted_index.impact | 58, 105 |
| abstract_inverted_index.little | 57 |
| abstract_inverted_index.longer | 32 |
| abstract_inverted_index.method | 95, 103, 122, 135 |
| abstract_inverted_index.mixing | 118 |
| abstract_inverted_index.model, | 110 |
| abstract_inverted_index.modern | 97 |
| abstract_inverted_index.neural | 7, 25 |
| abstract_inverted_index.purely | 147 |
| abstract_inverted_index.sparse | 120 |
| abstract_inverted_index.achieve | 137 |
| abstract_inverted_index.enables | 2 |
| abstract_inverted_index.enforce | 66 |
| abstract_inverted_index.forward | 22 |
| abstract_inverted_index.method. | 128 |
| abstract_inverted_index.observe | 41 |
| abstract_inverted_index.process | 34 |
| abstract_inverted_index.pruning | 37 |
| abstract_inverted_index.require | 29 |
| abstract_inverted_index.results | 130, 139 |
| abstract_inverted_index.shorter | 142 |
| abstract_inverted_index.systems | 4 |
| abstract_inverted_index.usually | 28 |
| abstract_inverted_index.Further, | 63 |
| abstract_inverted_index.However, | 13 |
| abstract_inverted_index.accuracy | 107 |
| abstract_inverted_index.approach | 87 |
| abstract_inverted_index.backward | 77 |
| abstract_inverted_index.hardware | 3 |
| abstract_inverted_index.inducing | 44 |
| abstract_inverted_index.networks | 8, 26 |
| abstract_inverted_index.quality. | 62 |
| abstract_inverted_index.sparsity | 1, 45, 68 |
| abstract_inverted_index.standard | 125 |
| abstract_inverted_index.training | 33, 61, 121, 127 |
| abstract_inverted_index.gradients | 48, 72 |
| abstract_inverted_index.iterative | 36 |
| abstract_inverted_index.training. | 149 |
| abstract_inverted_index.Exploiting | 0 |
| abstract_inverted_index.accelerate | 20 |
| abstract_inverted_index.comparable | 138 |
| abstract_inverted_index.eliminated | 116 |
| abstract_inverted_index.structured | 67, 101 |
| abstract_inverted_index.techniques | 18 |
| abstract_inverted_index.performance | 112 |
| abstract_inverted_index.retraining. | 39 |
| abstract_inverted_index.sparsifying | 94, 102 |
| abstract_inverted_index.Experimental | 129 |
| abstract_inverted_index.artificially | 43 |
| abstract_inverted_index.optimization | 17 |
| abstract_inverted_index.sparsity-centric | 16 |
| abstract_inverted_index.state-of-the-art | 85, 93 |
| abstract_inverted_index.energy-efficiently. | 12 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/7 |
| sustainable_development_goals[0].score | 0.8999999761581421 |
| sustainable_development_goals[0].display_name | Affordable and clean energy |
| citation_normalized_percentile |